Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 204 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0410. Min Act: -0.0004

Data Index: 882837 (C4 (Web Text))

Max Activating Token Index: 583

Text #1

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0389. Min Act: -0.0004

Data Index: 528440 (C4 (Web Text))

Max Activating Token Index: 220

Text #2

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0349. Min Act: -0.0004

Data Index: 1320168 (C4 (Web Text))

Max Activating Token Index: 376

Text #3

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0311. Min Act: -0.0004

Data Index: 1299895 (C4 (Web Text))

Max Activating Token Index: 850

Text #4

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0336. Min Act: -0.0004

Data Index: 723394 (C4 (Web Text))

Max Activating Token Index: 357

Text #5

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0331. Min Act: -0.0004

Data Index: 924935 (C4 (Web Text))

Max Activating Token Index: 456

Text #6

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0320. Min Act: -0.0004

Data Index: 1170243 (C4 (Web Text))

Max Activating Token Index: 441

Text #7

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0317. Min Act: -0.0004

Data Index: 666887 (C4 (Web Text))

Max Activating Token Index: 36

Text #8

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0336. Min Act: -0.0004

Data Index: 1283534 (C4 (Web Text))

Max Activating Token Index: 610

Text #9

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0339. Min Act: -0.0004

Data Index: 1085161 (C4 (Web Text))

Max Activating Token Index: 315

Text #10

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0330. Min Act: -0.0004

Data Index: 526152 (C4 (Web Text))

Max Activating Token Index: 155

Text #11

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0318. Min Act: -0.0004

Data Index: 1233157 (C4 (Web Text))

Max Activating Token Index: 348

Text #12

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0345. Min Act: -0.0004

Data Index: 348190 (C4 (Web Text))

Max Activating Token Index: 129

Text #13

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0322. Min Act: -0.0004

Data Index: 1083509 (C4 (Web Text))

Max Activating Token Index: 24

Text #14

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0333. Min Act: -0.0004

Data Index: 985415 (C4 (Web Text))

Max Activating Token Index: 593

Text #15

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0306. Min Act: -0.0004

Data Index: 752771 (C4 (Web Text))

Max Activating Token Index: 53

Text #16

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0321. Min Act: -0.0004

Data Index: 933596 (C4 (Web Text))

Max Activating Token Index: 909

Text #17

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0344. Min Act: -0.0004

Data Index: 311044 (C4 (Web Text))

Max Activating Token Index: 375

Text #18

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0314. Min Act: -0.0004

Data Index: 281534 (C4 (Web Text))

Max Activating Token Index: 315

Text #19

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0305. Min Act: -0.0004

Data Index: 503921 (C4 (Web Text))

Max Activating Token Index: 472